A cutterhead optimization system for full-face tunneling machines

Abstract

This invention relates to a cutterhead optimization system suitable for full-face tunneling machines, belonging to the field of cutterhead optimization control technology. The system includes: a data acquisition module for collecting various cutterhead operating parameter data within a preset time period and obtaining historical cutterhead wear data; a tunneling characteristic analysis module for analyzing tunneling characteristic information at the current moment; a wear prediction module for predicting the wear coefficient of the cutterhead at the current moment based on historical wear data and various cutterhead operating parameter data within the preset time period; a parameter generation module for generating the optimal working parameters of the cutterhead at the current moment based on the wear coefficient and tunneling characteristic information; and a control module for controlling the working parameters of the full-face rock tunneling machine to achieve the optimal working parameters of the cutterhead at the current moment. This invention achieves precise control of the cutterhead's working parameters, which can improve the cutterhead's working efficiency, reduce cutterhead wear, and extend its service life.

Description

Technical Field

[0001] This invention relates to the field of cutterhead optimization control technology, and in particular to a cutterhead optimization system suitable for full-face tunneling machines. Background Technology

[0002] To improve the speed of tunneling in rock mines, tunnel boring machines (TBMs) are now widely used in rock tunnel construction. During the rock-breaking process of tunnels and tunnels using TBMs, the operating parameters of the cutterhead directly affect tunneling efficiency, machine lifespan, and maintenance costs. Therefore, for TBMs, given the complex rock mass characteristics involved, optimized cutterhead design and operating parameter optimization are particularly important.

[0003] In traditional tunnel rock breaking processes, the optimization of the cutterhead of a full-face tunnel boring machine (TBM) often only adjusts the working parameters of the cutterhead based on its operating data, ignoring the rock mass information under complex geological conditions and the wear information of the cutterhead during rock breaking. This results in insufficient consideration of the cutterhead optimization of the full-face rock TBM, leading to poor optimization results and severe cutterhead wear. This not only reduces the life of the cutterhead but also leads to low rock breaking efficiency and poor tunnel forming accuracy. Summary of the Invention

[0004] To solve the above-mentioned technical problems, this invention provides a cutterhead optimization system suitable for full-face tunneling machines. The technical solution of this invention is as follows: A cutterhead optimization system suitable for full-face tunneling machines includes: The data acquisition module is used to collect various cutterhead operating parameters of the full-face rock tunnel boring machine during a preset time period before the current moment in the target tunnel operation, and to obtain the historical wear data of the cutterhead of the full-face rock tunnel boring machine. The tunneling characteristic analysis module is used to analyze the tunneling characteristic information at the current moment based on various cutterhead working condition parameter data and geological prediction data; The wear prediction module is used to predict the wear coefficient of the cutter head at the current moment based on historical wear data and various cutter head operating parameters within a preset time period. The parameter generation module is used to generate the optimal working parameters of the cutterhead at the current moment based on the wear coefficient and tunneling characteristic information of the cutterhead, with the rated power of the cutterhead as the target. The control module is used to control the operating parameters of the full-face rock tunnel boring machine so that the cutterhead reaches the optimal operating parameters at the current moment.

[0005] Preferably, the tunneling feature analysis module includes: The working condition feature extraction unit is used to filter multiple key cutterhead working condition parameter data from multiple cutterhead working condition parameter data, decompose each key cutterhead working condition parameter data into multiple intrinsic mode components according to the feature mode decomposition algorithm, filter the parameter features of each key cutterhead working condition parameter data according to each intrinsic mode component of each key cutterhead working condition parameter data, and combine the parameter features of all key cutterhead working condition parameter data to obtain the cutterhead working condition features. The geological prediction data processing unit is used to calculate the longitudinal wave velocity of the rock mass based on the geological prediction data, obtain the preset longitudinal wave velocity based on the rock mass type in the geological prediction data, and calculate the rock mass integrity coefficient based on the longitudinal wave velocity of the rock mass and the preset longitudinal wave velocity. The tunneling feature generation unit is used to combine cutterhead working condition features and rock mass integrity coefficient to generate tunneling feature information for the current moment.

[0006] Preferably, the working condition feature extraction unit includes: The standardization subunit standardizes various cutter head operating parameter data to obtain various standard cutter head operating parameter data. The filtering subunit is used to construct a covariance matrix based on various standard cutterhead operating parameter data, perform eigenvalue decomposition on the covariance matrix to obtain eigenvectors, calculate the variance contribution rate of each element in the eigenvectors, filter multiple elements as key elements based on the variance contribution rate, and use the various standard cutterhead operating parameter data corresponding to the multiple key elements as various key cutterhead operating parameter data. Here, each element represents the eigenvalue of a standard cutterhead operating parameter data. The decomposition subunit is used to iteratively decompose each key cutterhead working condition parameter data according to the eigenmode decomposition algorithm, and determine multiple intrinsic mode components after decomposition of each key cutterhead working condition parameter data according to the preset number of iterations. The parameter feature filtering subunit is used to calculate the energy of each intrinsic mode component of each key cutterhead working condition parameter data, sort all intrinsic mode components of each key cutterhead working condition parameter data according to the energy magnitude, and filter the preset number of intrinsic mode components with the largest energy as the parameter features of each key cutterhead working condition parameter data. The combination sub-unit is used to combine the parameter features of all key cutterhead operating parameter data to obtain the cutterhead operating feature.

[0007] Preferably, the screening subunit calculates the variance contribution rate R of any element μ in the feature vector a using formula (1): (1); In formula (1), ai represents the i-th element of eigenvector a, n represents the number of elements in eigenvector a, and max(ai) represents the maximum value of the elements in eigenvector a.

[0008] Preferably, the geological prediction data processing unit is used to: obtain the longitudinal wave velocity of the rock mass based on the geological prediction data. Historical seismic wave data from geological prediction data is obtained, and signal correction is performed after denoising the historical seismic wave data to obtain standard seismic wave data. The P-wave characteristics in the standard seismic wave data are then obtained. The P-wave velocity of the rock mass is calculated based on the P-wave characteristics of the standard seismic wave data.

[0009] Preferably, the wear prediction module includes: The comparison unit is used to perform time mapping processing on historical wear data and various cutter head operating condition parameter data within a preset time period of the cutter head to obtain a wear time series. The segmentation unit is used to segment the wear time series to obtain multiple segmented wear time series and obtain the wear prediction value of each segmented wear time series. The wear prediction unit is used to construct a wear prediction model based on the wear prediction value of each segment of the wear time series, and to predict the wear coefficient of the cutter head at the current moment based on the wear prediction model.

[0010] Preferably, the segmentation unit includes: The segmented sub-unit is used to acquire all wear measurement points in the wear time series, and the time interval between every two wear measurement points is used as the segmentation standard to obtain multiple segmented wear time series. The rate of change calculation subunit is used to obtain the single-parameter rate of change of each cutterhead condition parameter data for each segment of the wear time series; The wear prediction calculation subunit is used to perform weighted summation of the change rate of all single parameters and the preset weight coefficients of the data of each cutterhead working condition parameter for each segment of the wear time series to obtain the cumulative change. The historical wear data of each segment of the wear time series is superimposed with its cumulative change to obtain the wear prediction value of each segment of the wear time series.

[0011] Preferably, the wear prediction unit includes: The model fitting subunit performs time segmentation-wear prediction value fitting based on the wear prediction value of each segmented wear time series to obtain the wear prediction model; The wear coefficient determination sub-unit is used to determine the wear prediction value corresponding to the current moment in the wear prediction model, which is used as the wear coefficient of the cutter head at the current moment.

[0012] Preferably, the parameter generation module includes: The initial objective function construction unit is used to construct an initial objective function based on the cutterhead's working condition characteristics and the current working parameters, with the rated power of the cutterhead as the objective. The coefficient adjustment unit is used to calculate the rock mass adjustment coefficient of the rock mass integrity coefficient and the wear adjustment coefficient of the cutterhead at the current moment in the tunneling characteristic information; The objective function construction unit is used to accumulate the product of the rock mass integrity coefficient and the rock mass adjustment coefficient, and the product of the wear coefficient and the wear adjustment coefficient, into the initial objective function based on the tunneling characteristic information, so as to obtain the cutterhead optimization objective function; The parameter generation unit is used to calculate the optimal solution of the working parameters of the tool turret optimization objective function, and to generate the optimal working parameters of the tool turret at the current moment based on the optimal solution of the working parameters.

[0013] Preferably, the cutterhead working condition characteristics include torque, and the coefficient adjustment unit calculates the rock mass adjustment coefficient a1 of the rock mass integrity coefficient and the wear adjustment coefficient a2 of the cutterhead at the current moment in the tunneling characteristic information through formulas (2) and (3), respectively: (2); (3); In formula (2), exp() represents the exponential function, F represents the rock mass integrity coefficient, and F0 represents the preset standard rock mass integrity coefficient; In formula (3), σ represents the standard deviation of torque and U represents the mean of torque.

[0014] All of the above-mentioned optional technical solutions can be combined arbitrarily, and the present invention will not provide a detailed description of the structure after each combination.

[0015] By means of the above solution, the beneficial effects of the present invention are as follows: By collecting various cutterhead operating parameter data and historical wear data of the cutterhead within a preset time period before the current moment, and then combining it with geological prediction data to analyze the tunneling characteristics of the current moment, the optimization of the cutterhead comprehensively considers various types of operating parameter data, historical wear data and geological prediction data that will affect the cutterhead. This provides a multi-faceted data foundation for the cutterhead design optimization of full-face rock tunneling machines (cutter selection / cutter spacing / cutter tip and panel clearance, etc.). By predicting the current wear coefficient of the cutterhead and generating the optimal working parameters of the cutterhead based on the current wear coefficient and tunneling characteristic information, the optimization of the cutterhead incorporates multi-dimensional data affecting its working performance. This not only enables real-time optimization of the cutterhead's working parameters (thrust / torque / speed / penetration, etc.) but also achieves more precise control of these parameters. This not only improves the working efficiency of the cutterhead, reduces its wear, and extends its service life, but also enhances rock-breaking efficiency and tunnel forming accuracy.

[0016] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the structure of a cutterhead optimization system for a full-face tunneling machine provided in an embodiment of the present invention. Detailed Implementation

[0018] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0019] like Figure 1 As shown, this embodiment of the invention provides a cutterhead optimization system suitable for full-face tunneling machines, the modules of which include: The data acquisition module is used to collect various cutterhead operating parameters of the full-face rock tunnel boring machine during a preset time period before the current moment in the target tunnel operation, and to obtain the historical wear data of the cutterhead of the full-face rock tunnel boring machine. The tunneling characteristic analysis module is used to analyze the tunneling characteristic information at the current moment based on various cutterhead working condition parameter data and geological prediction data; The wear prediction module is used to predict the wear coefficient of the cutter head at the current moment based on historical wear data and various cutter head operating parameters within a preset time period. The parameter generation module is used to generate the optimal working parameters of the cutterhead at the current moment based on the wear coefficient and tunneling characteristic information of the cutterhead, with the rated power of the cutterhead as the target. The control module is used to control the operating parameters of the full-face rock tunnel boring machine so that the cutterhead reaches the optimal operating parameters at the current moment.

[0020] Specifically, in the data acquisition module, the full-face rock tunneling machine is a mechanical device used for rock-breaking engineering in mine rock tunnels. It can excavate the entire tunnel cross-section in one go without the need for traditional blasting or segmented excavation. The cutterhead, located at the front end of the full-face rock tunneling machine, is the core component for cutting rock. The target tunnel refers to the rock tunnel currently being excavated by the full-face rock tunneling machine. In this embodiment of the invention, the preset time period is generally 2 hours. The types of cutterhead operating parameter data include cutterhead torque, cutterhead speed, cutterhead load, cutterhead vibration, cutterhead thrust, and cutterhead penetration. The historical wear data of the cutterhead refers to the historical wear degree value of the cutterhead. In this embodiment of the invention, the historical wear data of the cutterhead is measured every 20 minutes.

[0021] In the tunneling characteristic analysis module, geological prediction data refers to the data on the prediction and analysis of rock strata during the tunneling process of the target tunnel, including rock strata type, historical seismic wave data, and rock hardness. Tunneling characteristic information includes at least the cutterhead working condition characteristics and rock mass integrity coefficient at the current moment.

[0022] In the wear prediction module, the wear coefficient is a value used to quantify the degree of wear on the cutter head.

[0023] In the parameter generation module, the rated power of the cutter head refers to the maximum power output value that the cutter head can continuously withstand during its design and manufacturing. In this embodiment of the invention, the rated power of the cutter head is approximately between 300kW and 800kW. The optimal operating parameters of the cutter head at the current moment include optimal rotational speed, optimal thrust, optimal torque, optimal penetration, optimal cutting force, and optimal cutting angle.

[0024] In the control module, when controlling the working parameters of the full-face rock tunneling machine, the working parameters are controlled by controlling the components corresponding to different types of working parameters. For example, based on the optimal speed in the optimal working parameters, the speed of the motor drive system is adjusted so that the cutterhead reaches the optimal speed.

[0025] In one specific embodiment, the tunneling feature analysis module includes: The working condition feature extraction unit is used to filter multiple key cutterhead working condition parameter data from multiple cutterhead working condition parameter data, decompose each key cutterhead working condition parameter data into multiple intrinsic mode components according to the feature mode decomposition algorithm, filter the parameter features of each key cutterhead working condition parameter data according to each intrinsic mode component of each key cutterhead working condition parameter data, and combine the parameter features of all key cutterhead working condition parameter data to obtain the cutterhead working condition features. The geological prediction data processing unit is used to calculate the longitudinal wave velocity of the rock mass based on the geological prediction data, obtain the preset longitudinal wave velocity based on the rock mass type in the geological prediction data, and calculate the rock mass integrity coefficient based on the longitudinal wave velocity of the rock mass and the preset longitudinal wave velocity. The tunneling feature generation unit is used to combine cutterhead working condition features and rock mass integrity coefficient to generate tunneling feature information for the current moment.

[0026] Specifically, in the working condition feature extraction unit, key cutterhead working condition parameter data refers to the data types selected from the cutterhead working condition parameter data that are important for describing the working conditions of the full-face rock tunnel boring machine. The Eigenmode Decomposition algorithm decomposes each key cutterhead working condition parameter data into multiple intrinsic mode components through layer-by-layer decomposition of local features. Each intrinsic mode component represents a parameter feature type, such as rotational frequency, bearing pressure, and blade load. The cutterhead working condition features are composed of multiple parameter features.

[0027] In the geological prediction data processing unit, the P-wave velocity in rock mass refers to the propagation speed of P-waves when seismic waves or ultrasonic waves propagate through rock mass. The preset P-wave velocity refers to the P-wave propagation speed of a rock mass of known type, based on experience or geological data, assuming that the rock mass has not been damaged or altered. The rock mass integrity coefficient is a parameter used to assess the integrity and density of rock mass.

[0028] In the tunneling feature generation unit, the tunneling feature information at the current moment is obtained by combining the cutterhead working condition features and the rock mass integrity coefficient.

[0029] In one specific embodiment, the working condition feature extraction unit includes: The standardization subunit standardizes various cutter head operating parameter data to obtain various standard cutter head operating parameter data. The filtering subunit is used to construct a covariance matrix based on various standard cutterhead operating parameter data, perform eigenvalue decomposition on the covariance matrix to obtain eigenvectors, calculate the variance contribution rate of each element in the eigenvectors, filter multiple elements as key elements based on the variance contribution rate, and use the various standard cutterhead operating parameter data corresponding to the multiple key elements as various key cutterhead operating parameter data. Here, each element represents the eigenvalue of a standard cutterhead operating parameter data. The decomposition subunit is used to iteratively decompose each key cutterhead working condition parameter data according to the eigenmode decomposition algorithm, and determine multiple intrinsic mode components after decomposition of each key cutterhead working condition parameter data according to the preset number of iterations. The parameter feature filtering subunit is used to calculate the energy of each intrinsic mode component of each key cutterhead working condition parameter data, sort all intrinsic mode components of each key cutterhead working condition parameter data according to the energy magnitude, and filter the preset number of intrinsic mode components with the largest energy as the parameter features of each key cutterhead working condition parameter data. The combination sub-unit is used to combine the parameter features of all key cutterhead operating parameter data to obtain the cutterhead operating feature.

[0030] Specifically, in the standardization sub-unit, standardization is achieved by performing maximum and minimum value standardization on various cutter head operating parameter data.

[0031] In the filtering sub-unit, the covariance matrix reflects the covariance among various standard cutterhead operating parameter data, i.e., the degree of correlation. For example, the element in the 5th row and 6th column of the covariance matrix represents the covariance between the fifth and sixth standard cutterhead operating parameter data. Eigenvalue decomposition is the process of decomposing the covariance matrix into eigenvalues ​​and eigenvectors. For example, the 8th element in the eigenvector represents the eigenvalue of the eighth standard cutterhead operating parameter data. The variance contribution rate describes the degree to which the eigenvalue corresponding to a certain standard cutterhead operating parameter data contributes to the eigenvector.

[0032] In the decomposition subunit, the Eigenmode Decomposition algorithm iteratively extracts the intrinsic modal components from the standard cutterhead operating parameter data, ultimately decomposing the standard cutterhead operating parameter data into multiple intrinsic modal components. The preset number of iterations is typically set to 10, at which point the number of intrinsic modal components is also 10.

[0033] In the parameter feature filtering subunit, the energy of a certain intrinsic mode component of a certain standard cutterhead working condition parameter data represents the ratio of that intrinsic mode component to the sum of squares of all intrinsic mode components of the standard cutterhead working condition parameter data; the preset number is generally 5.

[0034] In a specific embodiment, the screening subunit calculates the variance contribution rate R of any element μ in the feature vector a using formula (1): (1); In formula (1), ai represents the i-th element of eigenvector a, n represents the number of elements in eigenvector a, and max(ai) represents the maximum value of the elements in eigenvector a.

[0035] Specifically, formula (1) calculates the overall contribution rate of element μ and adds the penalty term of the penalty element μ to obtain the variance contribution rate R of element μ.

[0036] In one specific embodiment, the geological prediction data processing unit is used to: obtain the P-wave velocity of the rock mass based on the geological prediction data. Historical seismic wave data from geological prediction data is obtained, and signal correction is performed after denoising the historical seismic wave data to obtain standard seismic wave data. The P-wave characteristics in the standard seismic wave data are then obtained. The P-wave velocity of the rock mass is calculated based on the P-wave characteristics of the standard seismic wave data.

[0037] Specifically, historical seismic wave data is typically taken from 30 days of data. Noise denoising is achieved through an adaptive filtering algorithm in this embodiment. Signal correction in this embodiment involves adjusting the signal amplitude of the historical seismic wave data to compensate for the effects of seismic wave attenuation. P-wave characteristics refer to the amplitude of the vibration corresponding to the first received time point in the standard seismic wave data.

[0038] When calculating the P-wave velocity Kv of the rock mass based on the P-wave characteristics V of the standard seismic wave data V0, it is achieved through formula (4): (4).

[0039] In one specific embodiment, the wear prediction module includes: The comparison unit is used to perform time mapping processing on historical wear data and various cutter head operating condition parameter data within a preset time period of the cutter head to obtain a wear time series. The segmentation unit is used to segment the wear time series to obtain multiple segmented wear time series and obtain the wear prediction value of each segmented wear time series. The wear prediction unit is used to construct a wear prediction model based on the wear prediction value of each segment of the wear time series, and to predict the wear coefficient of the cutter head at the current moment based on the wear prediction model.

[0040] Specifically, in the comparison unit, time mapping processing refers to constructing a mapping relationship between the time node of each sampling point in the historical wear data and the corresponding time node in various toolhead operating parameter data. Then, by combining the mapping relationship, the various toolhead operating parameter data of all time nodes and the historical wear data, the wear time series is obtained.

[0041] In the segmented unit, the wear prediction value refers to the value obtained by predicting the future wear degree of the cutterhead based on the wear time series.

[0042] In the wear prediction unit, the wear prediction model is a model that describes the historical or future wear state of the cutterhead by modeling historical wear data.

[0043] In one specific embodiment, the segmentation unit includes: The segmented sub-unit is used to acquire all wear measurement points in the wear time series, and the time interval between every two wear measurement points is used as the segmentation standard to obtain multiple segmented wear time series. The rate of change calculation subunit is used to obtain the single-parameter rate of change of each cutterhead condition parameter data for each segment of the wear time series; The wear prediction calculation subunit is used to perform weighted summation of the change rate of all single parameters and the preset weight coefficients of the data of each cutterhead working condition parameter for each segment of the wear time series to obtain the cumulative change. The historical wear data of each segment of the wear time series is superimposed with its cumulative change to obtain the wear prediction value of each segment of the wear time series.

[0044] Specifically, in the segmented sub-unit, the wear measurement point refers to the time node of each measurement in the historical wear data. The time interval between any two wear measurement points is used as the segmentation standard. For example, if the time interval between two wear measurement points is 15 minutes, then the segmented wear time series formed by these two wear measurement points has a time length of 15 minutes.

[0045] In the rate of change calculation subunit, the single-parameter rate of change refers to the sum of the rates of change of a certain cutterhead working condition parameter data at all time nodes within each segmented wear time series.

[0046] In the wear prediction calculation subunit, the preset weighting coefficients for each cutterhead operating condition parameter data are predetermined from historical data, representing the influence coefficients of each cutterhead operating condition parameter data in the calculation of cumulative changes. The wear prediction value is obtained by superimposing the historical wear degree values ​​of the historical wear data of each segmented wear time series with the cumulative changes of the corresponding segmented wear time series.

[0047] In one specific embodiment, the wear prediction unit includes: The model fitting subunit performs time segmentation-wear prediction value fitting based on the wear prediction value of each segmented wear time series to obtain the wear prediction model; The wear coefficient determination sub-unit is used to determine the wear prediction value corresponding to the current moment in the wear prediction model, which is used as the wear coefficient of the cutter head at the current moment.

[0048] Specifically, in the model fitting sub-unit, the time segment-wear prediction value fitting process establishes a step function type wear prediction model by fitting the wear prediction value of each segment of the wear time series. In this model, the constant value of a certain step segment represents the wear prediction value within that time interval.

[0049] In the wear coefficient determination sub-unit, the current moment is input into the wear prediction model, and the wear prediction value of the tool turret at the current moment is output.

[0050] In one specific embodiment, the parameter generation module includes: The initial objective function construction unit is used to construct an initial objective function based on the cutterhead's working condition characteristics and the current working parameters, with the rated power of the cutterhead as the objective. The coefficient adjustment unit is used to calculate the rock mass adjustment coefficient of the rock mass integrity coefficient and the wear adjustment coefficient of the cutterhead at the current moment in the tunneling characteristic information; The objective function construction unit is used to accumulate the product of the rock mass integrity coefficient and the rock mass adjustment coefficient, and the product of the wear coefficient and the wear adjustment coefficient, into the initial objective function based on the tunneling characteristic information, so as to obtain the cutterhead optimization objective function; The parameter generation unit is used to calculate the optimal solution of the working parameters of the tool turret optimization objective function, and to generate the optimal working parameters of the tool turret at the current moment based on the optimal solution of the working parameters.

[0051] Specifically, in the initial objective function construction unit, an initial objective function is constructed based on the operating characteristics of the cutterhead and the current operating parameters, with the rated power of the cutterhead as the objective. The initial objective function can be a power function specific to the cutterhead industry.

[0052] In the coefficient adjustment unit, the rock mass adjustment coefficient is a parameter that adjusts the rock mass integrity coefficient. The wear adjustment coefficient is a parameter that adjusts the wear coefficient at the current moment based on tunneling characteristic information.

[0053] In the parameter generation unit, the optimal solution of the working parameters of the tool turret optimization objective function is calculated by applying Newton's iteration method to the tool turret optimization objective function.

[0054] In a specific embodiment, the cutterhead working condition characteristics include torque, and the coefficient adjustment unit calculates the rock mass adjustment coefficient a1 of the rock mass integrity coefficient and the wear adjustment coefficient a2 of the cutterhead at the current moment in the tunneling characteristic information through formulas (2) and (3), respectively: (2); (3); In formula (2), exp() represents the exponential function, F represents the rock mass integrity coefficient, and F0 represents the preset standard rock mass integrity coefficient; In formula (3), σ represents the standard deviation of torque and U represents the mean of torque.

[0055] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A cutterhead optimization system suitable for full-face tunneling machines, characterized in that, include: The data acquisition module is used to collect various cutterhead operating parameters of the full-face rock tunnel boring machine during a preset time period before the current moment in the target tunnel operation, and to obtain the historical wear data of the cutterhead of the full-face rock tunnel boring machine. The tunneling characteristic analysis module is used to analyze the tunneling characteristic information at the current moment based on various cutterhead working condition parameter data and geological prediction data; The wear prediction module is used to predict the wear coefficient of the cutterhead at the current moment based on historical wear data and various cutterhead operating parameters within a preset time period. The parameter generation module is used to generate the optimal working parameters of the cutterhead at the current moment based on the wear coefficient and tunneling characteristic information of the cutterhead, with the rated power of the cutterhead as the target. The control module is used to control the operating parameters of the full-face rock tunnel boring machine so that the cutterhead reaches the optimal operating parameters at the current moment.

2. The cutterhead optimization system for full-face tunneling machines according to claim 1, characterized in that, The tunneling feature analysis module includes: The working condition feature extraction unit is used to filter multiple key cutterhead working condition parameter data from multiple cutterhead working condition parameter data, decompose each key cutterhead working condition parameter data into multiple intrinsic mode components according to the feature mode decomposition algorithm, filter the parameter features of each key cutterhead working condition parameter data according to each intrinsic mode component of each key cutterhead working condition parameter data, and combine the parameter features of all key cutterhead working condition parameter data to obtain the cutterhead working condition features. The geological prediction data processing unit is used to calculate the longitudinal wave velocity of the rock mass based on the geological prediction data, obtain the preset longitudinal wave velocity based on the rock mass type in the geological prediction data, and calculate the rock mass integrity coefficient based on the longitudinal wave velocity of the rock mass and the preset longitudinal wave velocity. The tunneling feature generation unit is used to combine cutterhead working condition features and rock mass integrity coefficient to generate tunneling feature information for the current moment.

3. The cutterhead optimization system for full-face tunneling machines according to claim 2, characterized in that, The working condition feature extraction unit includes: The standardization subunit standardizes various cutter head operating parameter data to obtain various standard cutter head operating parameter data. The filtering subunit is used to construct a covariance matrix based on various standard cutterhead operating parameter data, perform eigenvalue decomposition on the covariance matrix to obtain eigenvectors, calculate the variance contribution rate of each element in the eigenvectors, filter multiple elements as key elements based on the variance contribution rate, and use the various standard cutterhead operating parameter data corresponding to the multiple key elements as various key cutterhead operating parameter data. Here, each element represents the eigenvalue of a standard cutterhead operating parameter data. The decomposition subunit is used to iteratively decompose each key cutterhead working condition parameter data according to the eigenmode decomposition algorithm, and determine multiple intrinsic mode components after decomposition of each key cutterhead working condition parameter data according to the preset number of iterations. The parameter feature filtering subunit is used to calculate the energy of each intrinsic mode component of each key cutterhead working condition parameter data, sort all intrinsic mode components of each key cutterhead working condition parameter data according to the energy magnitude, and filter the preset number of intrinsic mode components with the largest energy as the parameter features of each key cutterhead working condition parameter data. The combination sub-unit is used to combine the parameter features of all key cutterhead operating parameter data to obtain the cutterhead operating feature.

4. The cutterhead optimization system for full-face tunneling machines according to claim 3, characterized in that, The screening subunit calculates the variance contribution rate R of any element μ in the feature vector a using formula (1): （1）； In formula (1), ai represents the i-th element of eigenvector a, n represents the number of elements in eigenvector a, and max(ai) represents the maximum value of the elements in eigenvector a.

5. The cutterhead optimization system for full-face tunneling machines according to claim 2, characterized in that, The geological forecast data processing unit is used to obtain the longitudinal wave velocity of the rock mass based on the geological forecast data for: Historical seismic wave data are obtained from geological prediction data. After denoising the historical seismic wave data, signal correction is performed to obtain standard seismic wave data, and the P-wave characteristics in the standard seismic wave data are obtained. Calculate the P-wave velocity of the rock mass based on the P-wave characteristics of standard seismic wave data.

6. The cutterhead optimization system for full-face tunneling machines according to claim 1, characterized in that, The wear prediction module includes: The comparison unit is used to perform time mapping processing on the historical wear data of the cutter head and various cutter head operating condition parameter data within a preset time period to obtain the wear time series. The segmentation unit is used to segment the wear time series to obtain multiple segmented wear time series and obtain the wear prediction value of each segmented wear time series. The wear prediction unit is used to construct a wear prediction model based on the wear prediction value of each segment of the wear time series, and to predict the wear coefficient of the cutter head at the current moment based on the wear prediction model.

7. A cutterhead optimization system for full-face tunneling machines according to claim 6, characterized in that, The segmentation unit includes: The segmented sub-unit is used to acquire all wear measurement points in the wear time series, and the time interval between every two wear measurement points is used as the segmentation standard to obtain multiple segmented wear time series. The rate of change calculation subunit is used to obtain the single-parameter rate of change of each cutterhead condition parameter data for each segment of the wear time series; The wear prediction calculation subunit is used to perform weighted summation of the change rate of all single parameters and the preset weight coefficients of the data of each cutterhead working condition parameter for each segment of the wear time series to obtain the cumulative change. The historical wear data of each segment of the wear time series is superimposed with its cumulative change to obtain the wear prediction value of each segment of the wear time series.

8. A cutterhead optimization system for full-face tunneling machines according to claim 6 or 7, characterized in that, The wear prediction unit includes: The model fitting subunit performs time segmentation-wear prediction value fitting based on the wear prediction value of each segmented wear time series to obtain the wear prediction model; The wear coefficient determination sub-unit is used to determine the wear prediction value corresponding to the current moment in the wear prediction model, which is used as the wear coefficient of the cutter head at the current moment.

9. A cutterhead optimization system for full-face tunneling machines according to claim 2, characterized in that, The parameter generation module includes: The initial objective function construction unit is used to construct an initial objective function based on the cutterhead's working condition characteristics and the current working parameters, with the rated power of the cutterhead as the objective. The coefficient adjustment unit is used to calculate the rock mass adjustment coefficient of the rock mass integrity coefficient and the wear adjustment coefficient of the cutterhead at the current moment in the tunneling characteristic information; The objective function construction unit is used to accumulate the product of the rock mass integrity coefficient and the rock mass adjustment coefficient, and the product of the wear coefficient and the wear adjustment coefficient, into the initial objective function based on the tunneling characteristic information, so as to obtain the cutterhead optimization objective function; The parameter generation unit is used to calculate the optimal solution of the working parameters of the tool turret optimization objective function, and to generate the optimal working parameters of the tool turret at the current moment based on the optimal solution of the working parameters.

10. A cutterhead optimization system for a full-face tunneling machine according to claim 9, characterized in that, The cutterhead operating condition characteristics include torque. When calculating the rock mass adjustment coefficient a1 of the rock mass integrity coefficient in the tunneling characteristic information and the wear adjustment coefficient a2 of the cutterhead at the current moment, the coefficient adjustment unit is implemented by formula (2) and formula (3) respectively: （2）； （3）； In formula (2), exp() represents the exponential function, F represents the rock mass integrity coefficient, and F0 represents the preset standard rock mass integrity coefficient; In formula (3), σ represents the standard deviation of torque and U represents the mean of torque.

Images